zhangjinyangnwpu

yes, you need download the dataset by yourself, and specify the path with ``` parser.add_argument('--data_path',dest='data_path',default="../../dataset") ``` in main.py

Thanks for your attention, I will commit the weight file when I prepare them ready.

you can find the specific category in follow link, the color map generated by this repository not precisely controlled, just set with plt.pcolor(de_map, cmap='jet') https://www.ehu.eus/ccwintco/index.php?title=Hyperspectral_Remote_Sensing_Scenes

you can find model.py now in 1D or 2D or 3D methods, sorry added model.* in .gitignore

I will release the code later when I orginize them well, sorry for that, a little busy recently

There are no references, and I designed the classifier by myself, here I just show a demo that how to use 1D, 2D or 3D convolution. WaterVcc 于2018年9月11日周二 下午8:27写道： >...

added model.py to folder, sorry for writing model.* in .gitignore

python version is 3.6 and tensorflow version is 1.8，in deep learning based method, you can change the profile with parser in main file and just run main; in traditional machine...

Just you wish

I just use 9 classes in Indian Pines dataset due to the sample unbalance，if you want to use all categories, just ignore the code ``` # comment these code if...